@inproceedings{abouammoh-etal-2016-creation,
title = "Creation of comparable corpora for {E}nglish-{Urdu, Arabic, Persian}",
author = "Abouammoh, Murad and
Shah, Kashif and
Aker, Ahmet",
editor = "Calzolari, Nicoletta and
Choukri, Khalid and
Declerck, Thierry and
Goggi, Sara and
Grobelnik, Marko and
Maegaard, Bente and
Mariani, Joseph and
Mazo, Helene and
Moreno, Asuncion and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
month = may,
year = "2016",
address = "Portoro{\v{z}}, Slovenia",
publisher = "European Language Resources Association (ELRA)",
url = "https://aclanthology.org/L16-1663",
pages = "4193--4196",
abstract = "Statistical Machine Translation (SMT) relies on the availability of rich parallel corpora. However, in the case of under-resourced languages or some specific domains, parallel corpora are not readily available. This leads to under-performing machine translation systems in those sparse data settings. To overcome the low availability of parallel resources the machine translation community has recognized the potential of using comparable resources as training data. However, most efforts have been related to European languages and less in middle-east languages. In this study, we report comparable corpora created from news articles for the pair English ―{Arabic, Persian, Urdu} languages. The data has been collected over a period of a year, entails Arabic, Persian and Urdu languages. Furthermore using the English as a pivot language, comparable corpora that involve more than one language can be created, e.g. English- Arabic - Persian, English - Arabic - Urdu, English ― Urdu - Persian, etc. Upon request the data can be provided for research purposes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abouammoh-etal-2016-creation">
<titleInfo>
<title>Creation of comparable corpora for English-Urdu, Arabic, Persian</title>
</titleInfo>
<name type="personal">
<namePart type="given">Murad</namePart>
<namePart type="family">Abouammoh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kashif</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ahmet</namePart>
<namePart type="family">Aker</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marko</namePart>
<namePart type="family">Grobelnik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helene</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asuncion</namePart>
<namePart type="family">Moreno</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Portorož, Slovenia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Statistical Machine Translation (SMT) relies on the availability of rich parallel corpora. However, in the case of under-resourced languages or some specific domains, parallel corpora are not readily available. This leads to under-performing machine translation systems in those sparse data settings. To overcome the low availability of parallel resources the machine translation community has recognized the potential of using comparable resources as training data. However, most efforts have been related to European languages and less in middle-east languages. In this study, we report comparable corpora created from news articles for the pair English ―Arabic, Persian, Urdu languages. The data has been collected over a period of a year, entails Arabic, Persian and Urdu languages. Furthermore using the English as a pivot language, comparable corpora that involve more than one language can be created, e.g. English- Arabic - Persian, English - Arabic - Urdu, English ― Urdu - Persian, etc. Upon request the data can be provided for research purposes.</abstract>
<identifier type="citekey">abouammoh-etal-2016-creation</identifier>
<location>
<url>https://aclanthology.org/L16-1663</url>
</location>
<part>
<date>2016-05</date>
<extent unit="page">
<start>4193</start>
<end>4196</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Creation of comparable corpora for English-Urdu, Arabic, Persian
%A Abouammoh, Murad
%A Shah, Kashif
%A Aker, Ahmet
%Y Calzolari, Nicoletta
%Y Choukri, Khalid
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Grobelnik, Marko
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Helene
%Y Moreno, Asuncion
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16)
%D 2016
%8 May
%I European Language Resources Association (ELRA)
%C Portorož, Slovenia
%F abouammoh-etal-2016-creation
%X Statistical Machine Translation (SMT) relies on the availability of rich parallel corpora. However, in the case of under-resourced languages or some specific domains, parallel corpora are not readily available. This leads to under-performing machine translation systems in those sparse data settings. To overcome the low availability of parallel resources the machine translation community has recognized the potential of using comparable resources as training data. However, most efforts have been related to European languages and less in middle-east languages. In this study, we report comparable corpora created from news articles for the pair English ―Arabic, Persian, Urdu languages. The data has been collected over a period of a year, entails Arabic, Persian and Urdu languages. Furthermore using the English as a pivot language, comparable corpora that involve more than one language can be created, e.g. English- Arabic - Persian, English - Arabic - Urdu, English ― Urdu - Persian, etc. Upon request the data can be provided for research purposes.
%U https://aclanthology.org/L16-1663
%P 4193-4196
Markdown (Informal)
[Creation of comparable corpora for English-Urdu, Arabic, Persian](https://aclanthology.org/L16-1663) (Abouammoh et al., LREC 2016)
ACL